# DeepSeek-V4-Flash-0731 DSpark — AGENT-SERVING profile (2× GB10, TP=2).
#
# Fork of deepseek-v4-flash-eugr tuned for interactive agent traffic, applying
# the validated "agent-2048" profile from the SvangenStudios DGX-Spark
# agent-serving benchmarks (v0.1.1, measured 2026-08-02 on this exact stack:
# DeepSeek-V4-Flash-0731, DSpark k=5, 2× DGX Spark, TP=2, RoCE):
#   https://github.com/SvangenStudios/dgx-spark-agent-serving-benchmarks
#   configs/agent-2048.env  /  results/RESULTS.md §4
#
# The benchmark's headline finding: --max-num-batched-tokens is a FAIRNESS
# lever for agent workloads, not just a jitter lever. Against an ongoing
# decode stream, a 262K-token prefill at 2048 delivers 2.9× the decode share
# (5.0% vs 1.7%), 3.1× the decode tokens, 73% lower p95 output-chunk jitter,
# and +67% KV-pool capacity — for 7.7% prefill throughput. The launcher's
# whole purpose is agent serving (a model may be serving this very agent), so
# 2048 is the more correct default here.
#
# Mental model (benchmark §3): an LLM server is three nearly-independent
# engines — prefill (compute-bound, serializes), decode (bandwidth-bound,
# scales to ~N=4), admission (scheduler-bound, BLOCKED during long prefill).
# Chunk size governs how often decode gets a scheduling slot between prefill
# chunks; smaller = more slots. It does NOT fix new-request admission (a
# short request submitted during a large prefill waits until prefill
# completes — 221× normal TTFT in both profiles).
#
# Knob changes vs deepseek-v4-flash-eugr (everything else identical — same
# eugr image, same backends, same env):
#   --max-num-batched-tokens  8192 -> 2048   (the fairness lever)
#   --max-num-seqs            8    -> 6      (decode saturates ~N=4; 6 gives
#                                             headroom without inflating
#                                             worst-case latency)
#   --max-cudagraph-capture-size 64 -> 36    (= max_num_seqs * (k+1) = 6*6;
#                                             the k+1 multiple rule — the
#                                             benchmark notes k=5 rejects
#                                             MAX_NUM_SEQS=1 at boot)
#   --gpu-memory-utilization  0.85 -> 0.78   (benchmark: "0.80 boots but dies
#                                             under traffic"; GMU is a KV
#                                             lever, not a safety lever, when
#                                             weights dominate memory)
#   --max-model-len           auto -> 1048576  (benchmark's 1M working capacity
#                                             — verified 12/12 needles at
#                                             32K/128K/512K/900K)
#
# Trade-off: this profile costs ~7.7% prefill throughput vs the 8192 batch
# profile. Use deepseek-v4-flash-eugr (8192) for exclusive long-context batch
# jobs (512K–1M) with no concurrent agent traffic. See the batch-8192 profile
# in the benchmark repo for the opposite extreme.
#
# 3× Sparks (TP=3): bump tensor_parallel_size + required_nodes to 3 (the eugr
# image supports it per forum comment #28). k=5 unchanged (model-native).

engine = "vllm"
name = "DeepSeek V4 Flash DSpark (eugr b12x, agent 2048)"
docker_image = "eugr/spark-vllm-b12x:sm121"
model = "deepseek-ai/DeepSeek-V4-Flash-0731"
required_nodes = 2
tensor_parallel_size = 2
pipeline_parallel_size = 1
distributed_backend = "mp"
shm_size = "32gb"
docker_image_dir = "deepseek-v4-flash-eugr"

entrypoint = ["vllm", "serve"]

args = [
    "--kv-cache-dtype", "fp8",
    "--block-size", "256",
    "--load-format", "instanttensor",
    # 1M working capacity (benchmark §2: 12/12 needles at 32K–900K). A 900K
    # prefill takes ~15 min and starves everything — batch capacity, not an
    # interactive mode.
    "--max-model-len", "1048576",
    # Decode saturates around N≈4 (benchmark §3); 6 gives headroom without
    # inflating worst-case latency. cudagraph capture = max_num_seqs*(k+1)=36.
    "--max-num-seqs", "6",
    # FAIRNESS LEVER (benchmark §4): 2048 gives 2.9× the decode share under a
    # concurrent prefill vs 8192, +67% KV pool, 73% lower jitter, for 7.7%
    # prefill throughput. Use 8192 only for exclusive long-context batch jobs.
    "--max-num-batched-tokens", "2048",
    # = max_num_seqs * (k+1) = 6 * 6 (the k+1 multiple rule).
    "--max-cudagraph-capture-size", "36",
    # Benchmark finding: "0.80 boots but dies under traffic" — 0.78 is the
    # safe ceiling. GMU is a KV lever, not a safety lever, when weights
    # dominate memory (~77.7 GiB of ~119.6 GiB node).
    "--gpu-memory-utilization", "0.78",
    "--served-model-name", "deepseek-v4-flash",
    # Engine backends — b12x across attention / MoE / linear
    "--attention-backend", "B12X_MLA_SPARSE",
    "--moe-backend", "b12x",
    "--linear-backend", "b12x",
    # Prefix caching — agent frameworks build prompts append-only, so reuse is
    # 95.7–98.4% per turn (benchmark §9: divergence at the last token of the
    # previous prompt; only ~270–660 tokens re-prefilled per agent step).
    "--enable-prefix-caching",
    # Compilation
    "--compilation-config", """
'{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}'""",
    # DSpark speculative decoding — k=5 (DeepSeek-V4-Flash native
    # dspark_block_size). draft_sample_method per eugr recipe; draft attention
    # backend B12X_MLA_SPARSE. The baked mod makes the embedded draft load via
    # lazy safetensors while the target stays on InstantTensor.
    "--speculative-config", """
'{"method":"dspark","num_speculative_tokens":5,"draft_sample_method":"probabilistic","attention_backend":"B12X_MLA_SPARSE"}'""",
    # Tokenizer / reasoning — reasoning-config pins the parser + empty
    # reasoning markers (deepseek_v4 tokenizer mode emits them itself).
    "--tokenizer-mode", "deepseek_v4",
    "--tool-call-parser", "deepseek_v4",
    "--reasoning-parser", "deepseek_v4",
    "--reasoning-config", """
'{"reasoning_parser":"deepseek_v4","reasoning_start_str":"","reasoning_end_str":""}'""",
    "--enable-auto-tool-choice",
    "--generation-config", "vllm",
    "--default-chat-template-kwargs.thinking=true",
    "--default-chat-template-kwargs.reasoning_effort=high",
    "--disable-custom-all-reduce",
    "--trust-remote-code",
]

# Persistent vLLM compile cache (speeds up restarts). Mounted at vLLM's
# default cache root for root (/root/.cache/vllm); the HF cache is already
# mounted at /root/.cache/huggingface by the launcher. Shares the eugr
# recipe's cache dir (same image/backends — compile artifacts are reusable).
[[extra_mounts]]
host = "~/.cache/vllm-ds4-eugr"
container = "/root/.cache/vllm"

[env]
# --- b12x + compile (from eugr's recipe env, verbatim) ---
CUTE_DSL_ARCH = "sm_121a"
VLLM_USE_AOT_COMPILE = "1"
VLLM_USE_BREAKABLE_CUDAGRAPH = "0"
VLLM_USE_MEGA_AOT_ARTIFACT = "-1"
VLLM_MEMORY_PROFILE_INCLUDE_ATTN = "1"
VLLM_USE_FLASHINFER_SAMPLER = "1"
VLLM_USE_B12X_WO_PROJECTION = "1"
VLLM_USE_B12X_MHC = "1"
VLLM_USE_B12X_FP8_GEMM = "1"
VLLM_USE_B12X_MOE = "1"
VLLM_USE_B12X_SPARSE_INDEXER = "1"
VLLM_USE_V2_MODEL_RUNNER = "1"
B12X_MLA_SM120_UNIFIED = "1"
B12X_MOE_FORCE_A8 = "1"

# --- arch / memory / GPU isolation (operational on the sm121 cluster) ---
TORCH_CUDA_ARCH_LIST = "12.1a"
PYTORCH_CUDA_ALLOC_CONF = "expandable_segments:True"
OMP_NUM_THREADS = "4"
CUDA_VISIBLE_DEVICES = "0"
CUDA_DEVICE_ORDER = "PCI_BUS_ID"
CUDA_CACHE_MAXSIZE = "4294967296"

# --- offline ---
HF_HUB_OFFLINE = "1"

# --- NCCL overrides (GB10 single-NIC tuning; image-agnostic — mirrors
#     recipes/deepseek-v4-flash. The launcher still injects IB/HCA/socket
#     vars from the cluster config; these are recipe-level extras.) ---
NCCL_P2P_LEVEL = "SYS"
NCCL_CUMEM_ENABLE = "0"
NCCL_IB_TIMEOUT = "24"
NCCL_IB_QPS_PER_CONNECTION = "8"
NCCL_BUFFERSIZE = "16777216"
NCCL_SOCKET_FAMILY = "inet"

# PCIe allreduce not needed on GB10 single-NIC
VLLM_ENABLE_PCIE_ALLREDUCE = "0"
VLLM_PCIE_ALLREDUCE_BACKEND = "cpp"